| 1. |
- Rousopoulou, Vaia, et al.
(author)
-
Cognitive analytics platform with AI solutions for anomaly detection
- 2022
-
In: Computers in industry (Print). - : Elsevier BV. - 0166-3615 .- 1872-6194. ; 134, s. 103555-103555
-
Journal article (peer-reviewed)abstract
- This work presents a cognitive analytics platform for anomaly detection which is capable to handle, analyze and exploit resourcefully machine data from a shop-floor of factory, so as to support the emerging and growing needs of manufacturing industry. The introduced system contributes to industrial digitization and creation of smart factories by providing a generic platform which is a complete solution supporting standards-based factory connectivity, data management, various AI models training and comparisons, live predictions and real-time visualizations. The proposed system is built on a micro-service architecture, in order to be extendable and adaptive over time, and contains three core modules, the Data Acquisition, the Knowledge Management and the Predictive maintenance, which contribute to machine failure prediction and activate predictive maintenance procedures, to efficient production schemes and decision making, to monitor anomalies and handle unforeseen conditions, to predict future behaviours on time series etc. The proposed platform utilizes continuous re-training mechanisms enabling a self learning approach for the delivery of AI solutions, usable also for various production data, guaranteeing the quality of results without continuous monitoring and human-resources allocation for AI models’ retraining. This cognitive platform is supported by machine learning techniques and deep learning architectures in order to achieve the desired performance in the management of factory processes and needs. All the information generated by the proposed platform is provided to the end user through a user interface that utilizes advanced visualization techniques.
|
|
| 2. |
- Terzis, Gerasimos, et al.
(author)
-
The degree of p70(S6k) and S6 phosphorylation in human skeletal muscle in response to resistance exercise depends on the training volume.
- 2010
-
In: European Journal of Applied Physiology. - : Springer Science and Business Media LLC. - 1439-6319 .- 1439-6327. ; 110:4, s. 835-43
-
Journal article (peer-reviewed)abstract
- Regular performance of resistance exercise induces an increase in skeletal muscle mass, however, the molecular mechanisms underlying this effect are not yet fully understood. The purpose of the present investigation was to examine acute changes in molecular signalling in response to resistance exercise involving different training volumes. Eight untrained male subjects carried out one, three and five sets of 6 repetition maximum (RM) in leg press exercise in a random order. Muscle biopsies were taken from the vastus lateralis both prior to and 30 min after each training session and the effect on protein signalling was studied. Phosphorylation of Akt was not altered significantly after any of the training protocols, whereas that of the mammalian target of rapamycin was enhanced to a similar extent by training at all three volumes. The phosphorylation of p70S6 kinase (p70(S6k)) was elevated threefold after 3 × 6 RM and sixfold after 5 × 6 RM, while the phosphorylation of S6 was increased 30- and 55-fold following the 3 × 6 RM and 5 × 6 RM exercises, respectively. Moreover, the level of the phosphorylated form of the gamma isoform of p38 MAPK was enhanced three to fourfold following each of the three protocols, whereas phosphorylation of ERK1/2 was unchanged 30 min following exercise. These findings indicate that when exercise is performed in a fasted state, the increase in phosphorylation of signalling molecules such as p70(S6k) and the S6 ribosomal protein in human muscle depends on the exercise volume.
|
|
